Daphne Koller

Filling missing components in yeast metabolic pathways (2009)

In typical classification tasks, we seek a function which assigns a label to a single object. Kernel-based approaches, such as support vector machines (SVMs), which maximize the margin of confidence...

Gal Chechik, Aviv Regev, Daphne Koller

using heterogeneous data

5 Probabilistic Relational Models (2009)

Lise Getoor, Nir Friedman, Daphne Koller, Avi Pfeffer, Ben Taskar

Probabilistic relational models (PRMs) are a rich representation language for structured statistical models. They combine a frame-based logical representation with probabilistic semantics based on...

7 Probabilistic Entity-Relationship Models, PRMs, and Plate (2009)

David Heckerman, Chris Meek, Daphne Koller

In this chapter, we introduce a graphical language for relational data called the probabilistic entity-relationship (PER) model. The model is an extension of the entity-relationship model, a common...

Online Word Games for Semantic Data Collection (2009)

David Vickrey, Aaron Bronzan, William Choi, Aman Kumar, Jason Turner-maier, Arthur Wang, ...

Obtaining labeled data is a significant obstacle for many NLP tasks. Recently, online games have been proposed as a new way of obtaining labeled data; games attract users by being fun to play. In...

Cascaded Classification Models: Combining Models for Holistic Scene Understanding (2009)

Geremy Heitz, Stephen Gould, Ashutosh Saxena, Daphne Koller

One of the original goals of computer vision was to fully understand a natural scene. This requires solving several sub-problems simultaneously, including object detection, region labeling, and...

Constrained Approximate Maximum Entropy Learning of Markov Random Fields (2009)

Varun Ganapathi, David Vickrey, John Duchi, Daphne Koller

Parameter estimation in Markov random fields (MRFs) is a difficult task, in which inference over the network is run in the inner loop of a gradient descent procedure. Replacing exact inference with...

Projected Subgradient Methods for Learning Sparse Gaussians (2009)

John Duchi, Stephen Gould, Daphne Koller

Gaussian Markov random fields (GMRFs) are useful in a broad range of applications. In this paper we tackle the problem of learning a sparse GMRF in a high-dimensional space. Our approach uses the...

Abstract Fast Algorithms for Finding Randomized Strategies in Game Trees (2009)

Daphne Koller, Nimrod Megiddo, Bernhard Von Stengel

Interactions among agents can be conveniently described by game trees. In order to analyze a game, it is important to derive optimal (or equilibrium) strategies for the different players. The...

Max-margin Classification of Data with Absent Features (2009)

Geremy Heitz, Gal Elidan, Pieter Abbeel, Daphne Koller, Nello Cristianini

We consider the problem of learning classifiers in structured domains, where some objects have a subset of features that are inherently absent due to complex relationships between the features....

LOOPS: Localizing Object Outlines using Probabilistic Shape (2008)

Many domains are naturally organized in an abstraction hierarchy or taxonomy, where the instances in “nearby ” classes in the taxonomy are similar. In this paper, we provide a general...

Geremy Heitz, Gal Elidan, Benjamin Packer, Daphne Koller

Abstract. Discriminative tasks, including object categorization and detection, are central components of high-level computer vision. However, sometimes we are interested in more refined aspects of...

We present a novel discriminative approach to parsing inspired by the large-margin criterion underlying support vector machines. Our formulation uses a factorization analogous to the standard dynamic...

Gal Elidan, Noam Lotner, Nir Friedman, Daphne Koller

A serious problem in learning probabilistic models is the presence of hidden variables. These variables are not observed, yet interact with several of the observed variables. As such, they induce...

Gal Elidan, Noam Lotner, Nir Friedman, Daphne Koller

A serious problem in learning probabilistic models is the presence of hidden variables. These variables are not observed, yet interact with several of the observed variables. As such, they induce...

We present a novel discriminative approach to parsing inspired by the large-margin criterion underlying support vector machines. Our formulation uses a factorization analogous to the standard dynamic...

Ignorable Information in Multi-Agent Scenarios (2008)

We propose a new approach to the problem of searching a space of stochastic controllers for a Markov decision process (MDP) or a partially observable Markov decision process (POMDP). Following...

Milch, Brian, Koller, Daphne

In some multi-agent scenarios, identifying observations that an agent can safely ignore reduces exponentially the size of the agent's strategy space and hence the time required to find a Nash...

Ignorable Information in Multi-Agent Scenarios (2008)

Milch, Brian, Koller, Daphne

In some multi-agent scenarios, identifying observations that an agent can safely ignore reduces exponentially the size of the agent's strategy space and hence the time required to find a Nash...

We present a novel discriminative approach to parsing inspired by the large-margin criterion underlying support vector machines. Our formulation uses a factorization analogous to the standard dynamic...

Rajat Raina, Andrew Y. Ng, Daphne Koller

Many applications of supervised learning require good generalization from limited labeled data. In the Bayesian setting, we can use an informative prior to try to achieve this goal by encoding useful...

We present a principled and efficient planning algorithm for cooperative multiagent dynamic systems. A striking feature of our method is that the coordination and communication between the agents is...

genome-wide (2008)

Haidong Wang, Eran Segal, Asa Ben-hur, Daphne Koller, Douglas L. Brutlag

protein-protein interaction sites on a

genome-wide (2008)

Haidong Wang, Eran Segal, Asa Ben-hur, Daphne Koller, Douglas L. Brutlag

protein-protein interaction sites on a

genome-wide (2008)

Haidong Wang, Eran Segal, Asa Ben-hur, Daphne Koller, Douglas L. Brutlag

protein-protein interaction sites on a

Gal Elidan, Noam Lotner, Nir Friedman, Daphne Koller

A serious problem in learning probabilistic models is the presence of hidden variables. These variables are not observed, yet interact with several of the observed variables. As such, they induce...

Inference is a key component in learning probabilistic models from partially observable data. When learning temporal models, each of the many inference phases requires a complete traversal over a...

Downloaded from (2008)

Sebastian Thrun, Yufeng Liu, Daphne Koller, Andrew Y. Ng, Zoubin Ghahramani, Hugh Durrant-whyte, ...

Citations (this article cites 9 articles hosted on the

Many domains are naturally organized in an abstraction hierarchy or taxonomy, where the instances in “nearby ” classes in the taxonomy are similar. In this paper, we provide a general...

We present a principled and efficient planning algorithm for cooperative multiagent dynamic systems. A striking feature of our method is that the coordination and communication between the agents is...

We propose a new approach to the problem of searching a space of stochastic controllers for a Markov decision process (MDP) or a partially observable Markov decision process (POMDP). Following...

Gal Elidan, Noam Lotner, Nir Friedman, Daphne Koller

A serious problem in learning probabilistic models is the presence of hidden variables. These variables are not observed, yet interact with several of the observed variables. As such, they induce...

Computer Science Dept, Joseph Y. Halpern, Adam J. Grove, Daphne Koller

An intelligent agent will often be uncertain about various properties of its environment, and when acting in that environment it will frequently need to quantify its uncertainty. For example, if the...

We present a novel discriminative approach to parsing inspired by the large-margin criterion underlying support vector machines. Our formulation uses a factorization analogous to the standard dynamic...

Adam J. Grove, Daphne Koller, Joseph Y. Halpern

Motivated by problems that arise in computing degrees of belief, we consider the problem of computing asymptotic conditional probabilities for first-order sentences. Given first-order sentences ϕ...

ASYMPTOTIC CONDITIONAL PROBABILITIES: THE UNARY (2008)

We propose a new approach to the problem of searching a space of stochastic controllers for a Markov decision process (MDP) or a partially observable Markov decision process (POMDP). Following...

Abstract. Motivated by problems that arise in computing degrees of belief, we consider the problem of computing asymptotic conditional probabilities for first-order sentences. Given firstorder...

We present a novel discriminative approach to parsing inspired by the large-margin criterion underlying support vector machines. Our formulation uses a factorization analogous to the standard dynamic...

Adam J. Grove, Daphne Koller, Joseph Y. Halpern

Motivated by problems that arise in computing degrees of belief, we consider the problem of computing asymptotic conditional probabilities for first-order sentences. Given first-order sentences ϕ...

ASYMPTOTIC CONDITIONAL PROBABILITIES: THE UNARY (2008)

Integrating Visual and Range Data for Robotic Object Detection (2008)

Abstract. Motivated by problems that arise in computing degrees of belief, we consider the problem of computing asymptotic conditional probabilities for first-order sentences. Given firstorder...

Gould, Stephen, Baumstarck, Paul, Quigley, Morgan, Ng, Andrew Y., Koller, Daphne

The problem of object detection and recognition is a notoriously difficult one, and one that has been the focus of much work in the computer vision and robotics communities. Most work has...

Integrating Visual and Range Data for Robotic Object Detection (2008)

Gould, Stephen, Baumstarck, Paul, Quigley, Morgan, Ng, Andrew Y., Koller, Daphne

The problem of object detection and recognition is a notoriously difficult one, and one that has been the focus of much work in the computer vision and robotics communities. Most work has...

A protein domain-based interactome network for C. elegans early embryogenesis (2008)

Boxem, Mike, Maliga, Zoltan, Klitgord, Niels, Li, Na, Lemmens, Irma, Mana, Miyeko, ...

Many protein-protein interactions are mediated through independently folding modular domains. Proteome-wide efforts to model protein-protein interaction or "interactome" networks have largely ignored...

Generating New Beliefs From Old Fahiem Bacchus (2007)

Computer Science Dept, Adam J. Grove, Joseph Y. Halpern, Daphne Koller

In previous work [BGHK92, BGHK93], we have studied the random-worlds approach---a particular (and quite powerful) method for generating degrees of belief (i.e., subjective probabilities) from a...

y (2007)

Probability Estimation in face of Irrelevant Information (2007)

Abstract. The subject of this paper is finding small sample spaces for joint distributions of n discrete random variables. Such distributions are often only required to obey a certain limited set of...

Hebrew University (2007)

Nir Friedman, Lise Getoor, Daphne Koller, Avi Pfeffer

A large portion of real-world data is stored in commercial relational database systems. In contrast, most statistical learning methods work only with "flat " data representations....

Adam J. Grove, Daphne Koller

In this paper, we consider one aspect of the problem of applying decision theory to the design of agents that learn how to make decisions under uncertainty. This aspect concerns how an agent can...

Aviv Regev (2007)

Eran Segal, Bauer Ctr, Daphne Koller, Nir Friedman

Methods for learning Bayesian networks can discover dependency structure between observed variables. Although these methods are useful in many applications, they run into computational and...

btaskar @ cs.stanford. edu (2007)

Lise Getoor, Ben Taskar, Daphne Koller

koller @ cs.stanford. edu Estimating the result size of complex queries that involve selection on multiple attributes and the join of several relations is a difficult but fundamental task in database...

dvickrey @ cs.stanford. edu (2007)

David Vickrey, Daphne Koller

koller @ cs.stanford. edu Consider the problem of a group of agents trying to find a stable strategy profile for a joint interaction. A standard approach is to describe the situation as a single...

By (2007)

Mehran Sahami, Daphne Koller, Marti Hearst, Nils J. Nilsson

ii

DRAFT: Accepted in Advances in Neural Information Processing Systems NIPS-14, 2001. Multiagent Planning with Factored MDPs (2007)

Bernhard Von Stengel, Daphne Koller

We present a new, principled and efficient planning algorithm for cooperative multi-agent dynamic systems. A striking feature of our method is that the coordination and communication between the...

and (2007)

(page numbers in this manuscript match only approximately) In a noncooperative game, a team is a set of players that have identical payoffs. We investigate zero-sum games where a team of several...

1 (2007)

Eran Segal, Ben Taskar, Audrey Gasch, Nir Friedman, Daphne Koller

Clustering is commonly used for analyzing gene expression data. Despite their successes, clustering methods suffer from a number of limitations. First, these methods reveal similarities that exist...

Forming beliefs about a changing world Fahiem Bacchus (2007)

Abstract Fast Algorithms for Finding Randomized Strategies in Game Trees (2007)

The situation calculus is a popular technique for reasoning about action and change. However, its restriction to a firstorder syntax and pure deductive reasoning makes it unsuitable in many contexts....

Daphne Koller, Nimrod Megiddo Y

Interactions among agents can be conveniently described by game trees. In order to analyze a game, it is important to derive optimal (or equilibrium) strategies for the di erent players. The standard...

Fahiem Bacchus (2007)

Adam Grove, Joseph Y. Halpern, Daphne Koller

A Response to "Believing on the basis of evidence"

InSite: a computational method for identifying protein-protein interaction binding sites on a proteome-wide scale (2007)

Wang, Haidong, Segal, Eran, Ben-Hur, Asa, Li, Qian-Ru, Vidal, Marc, Koller, Daphne

Abstract We propose InSite, a computational method that integrates high-throughput protein and sequence data to infer the specific binding regions of interacting protein pairs. We compared our...

Learning a meta-level prior for feature relevance from multiple related tasks (2007)

Su-in Lee, Vassil Chatalbashev, David Vickrey, Daphne Koller

In many prediction tasks, selecting relevant features is essential for achieving good generalization performance. Most feature selection algorithms consider all features to be a priori equally likely...

Using combinatorial optimization within max-product belief propagation (2007)

John Duchi, Daniel Tarlow, Gal Elidan, Daphne Koller

In general, the problem of computing a maximum a posteriori (MAP) assignment in a Markov random field (MRF) is computationally intractable. However, in certain subclasses of MRF, an optimal or...

Learning a meta-level prior for feature relevance from multiple related tasks (2007)

Su-in Lee, Vassil Chatalbashev, David Vickrey, Daphne Koller

In many prediction tasks, selecting relevant features is essential for achieving good generalization performance. Most feature selection algorithms consider all features to be a priori equally likely...

Learning a meta-level prior for feature relevance from multiple related tasks (2007)

Su-in Lee, Vassil Chatalbashev, David Vickrey, Daphne Koller

In many prediction tasks, selecting relevant features is essential for achieving good generalization performance. Most feature selection algorithms consider all features to be a priori equally likely...

Reasoning at the right time granularity (2007)

Suchi Saria, Uri Nodelman, Daphne Koller

Most real-world dynamic systems are composed of different components that often evolve at very different rates. In traditional temporal graphical models, such as dynamic Bayesian networks, time is...

Diego Jorquera Toward Optimal Feature Selection (2007)

Daphne Koller, Mehran Sahami, Diego Jorquera

Our context: supervised learning (or, more specifically, classification) Our motivation: reducing the dimensionality of our feature space (that is, reducing the number of features used)

International Journal of Computer Vision DOI 10.1007/s11263-008-0140-x Multi-Class Segmentation with Relative Location Prior (2007)

Stephen Gould, Jim Rodgers, David Cohen, Gal Elidan, Daphne Koller

Abstract Multi-class image segmentation has made significant advances in recent years through the combination of local and global features. One important type of global feature is that of inter-class...

Max-margin classification of incomplete data (2007)

Gal Chechik, Geremy Heitz, Gal Elidan, Pieter Abbeel, Daphne Koller

We consider the problem of learning classifiers for structurally incomplete data, where some objects have a subset of features inherently absent due to complex relationships between the features. The...

interaction binding sites on a proteome-wide scale (2007)

Haidong Wang, Eran Segal, Asa Ben-hur, Qian-ru Li, Marc Vidal, Daphne Koller

InSite: a computational method for identifying protein-protein

A Continuation Method for Nash Equilibria in Structured Games (2006)

Blum, Ben, Shelton, Christian R, Koller, Daphne

Structured game representations have recently attracted interest as models for multiagent artificial intelligence scenarios, with rational behavior most commonly characterized by Nash equilibria....

Simultaneous Mapping and Localization with Sparse Extended Information Filters: Theory and Initial Results (revised) (2006)

Thrun, Sebastian, Koller, Daphne, Ghahramani, Zoubin, Durrant-Whyte, Hugh, Ng, Andrew Y.

This paper describes a scalable algorithm for the simultaneous localization and mapping (SLAM) problem. SLAM is the problem of determining the location of environmental features with a roving robot....

Simultaneous Mapping and Localization with Sparse Extended Information Filters: Theory and Initial Results (revised) (2006)

Thrun, Sebastian, Koller, Daphne, Ghahramani, Zoubin, Durrant-Whyte, Hugh

This paper describes a scalable algorithm for the simultaneous localization and mapping (SLAM) problem. SLAM is the problem of determining the location of environmental features with a roving robot....

Temporal and cross-subject probabilistic models for fmri prediction tasks (2006)

Alexis Battle, Gal Chechik, Daphne Koller

We present a probabilistic model applied to the fMRI video rating prediction task of the Pittsburgh Brain Activity Interpretation Competition (PBAIC) [2]. Our goal is to predict a time series of...

Reprints (2006)

Su-in Lee, Aimée M. Dudley, George M. Church, Daphne Koller, Su-in Lee, Aimée M. Dudley, ...

Identifying regulatory mechanisms using individual variation reveals key role for chromatin modification

Efficient structure learning of Markov networks using L1regularization (2006)

Su-in Lee, Varun Ganapathi, Daphne Koller

Markov networks are widely used in a wide variety of applications, in problems ranging from computer vision, to natural language, to computational biology. In most current applications, even those...

Learning Factor Graphs in Polynomial Time and Sample Complexity (2006)

Pieter Abbeel, Daphne Koller, Andrew Y. Ng

We study the computational and sample complexity of parameter and structure learning in graphical models. Our main result shows that the class of factor graphs with bounded degree can be learned in...

Constructing informative priors using transfer learning (2006)

Rajat Raina, Andrew Y. Ng, Daphne Koller

Many applications of supervised learning require good generalization from limited labeled data. In the Bayesian setting, we can try to achieve this goal by using an informative prior over the...

Temporal and cross-subject probabilistic models for fmri prediction tasks (2006)

Alexis Battle, Gal Chechik, Daphne Koller

We present a probabilistic model applied to the fMRI video rating prediction task of the Pittsburgh Brain Activity Interpretation Competition (PBAIC) [2]. Our goal is to predict a time series of...

Efficient structure learning of Markov networks using L1regularization (2006)

Su-in Lee, Varun Ganapathi, Daphne Koller

Markov networks are commonly used in a wide variety of applications, ranging from computer vision, to natural language, to computational biology. In most current applications, even those that rely...

Learning factor graphs in polynomial time and sample complexity (2006)

Pieter Abbeel, Daphne Koller, Andrew Y. Ng, Sanjoy Dasgupta

We study the computational and sample complexity of parameter and structure learning in graphical models. Our main result shows that the class of factor graphs with bounded degree can be learned in...

Constructing informative priors using transfer learning (2006)

Rajat Raina, Andrew Y. Ng, Daphne Koller

Many applications of supervised learning require good generalization from limited labeled data. In the Bayesian setting, we can try to achieve this goal by using an informative prior over the...

Efficient structure learning of Markov networks using L1regularization (2006)

Su-in Lee, Varun Ganapathi, Daphne Koller

Markov networks are widely used in a wide variety of applications, in problems ranging from computer vision, to natural language, to computational biology. In most current applications, even those...

Efficient structure learning of Markov networks using ℓ1-regularization. Neural Information Processing Systems (2006)

Su-in Lee, Varun Ganapahthi, Daphne Koller

Markov networks are widely used in a wide variety of applications, in problems ranging from computer vision, to natural language, to computational biology. In most current applications, even those...

Word-Sense Disambiguation for Machine Translation (2005)

David Vickrey, Luke Biewald, Marc Teyssier, Daphne Koller

In word sense disambiguation, a system attempts to determine the sense of a word from contextual features. Major barriers to building a high-performing word sense disambiguation system include the...

Learning module networks (2005)

Eran Segal, Daphne Koller, Nir Friedman, Tommi Jaakkola

Methods for learning Bayesian networks can discover dependency structure between observed variables. Although these methods are useful in many applications, they run into computational and...

Learning Structured Prediction Models: A Large Margin Approach (2005)

Ben Taskar Taskar, Vassil Chatalbashev, Daphne Koller, Carlos Guestrin

We consider large margin estimation in a broad range of prediction models where inference involves solving combinatorial optimization problems, for example, weighted graphcuts or matchings. Our goal...

Learning module networks (2005)

Eran Segal, Daphne Koller, Nir Friedman, Tommi Jaakkola

Methods for learning Bayesian networks can discover dependency structure between observed variables. Although these methods are useful in many applications, they run into computational and...

Discriminative learning of Markov random fields for segmentation of 3d scan data (2005)

Dragomir Anguelov, Ben Taskar, Vassil Chatalbashev, Daphne Koller, Dinkar Gupta, Geremy Heitz, ...

We address the problem of segmenting 3D scan data into objects or object classes. Our segmentation framework is based on a subclass of Markov Random Fields (MRFs) which support efficient graph-cut...

SCAPE: shape completion and animation of people (2005)

Dragomir Anguelov, Praveen Srinivasan, Daphne Koller, Sebastian Thrun, Jim Rodgers, James Davis

Figure 1: Animation of a motion capture sequence taken for a subject, of whom we have a single body scan. The muscle deformations are synthesized automatically from the space of pose and body shape...

Discriminative learning of Markov random fields for segmentation of 3d scan data (2005)

Dragomir Anguelov, Ben Taskar, Vassil Chatalbashev, Daphne Koller, Dinkar Gupta, Geremy Heitz, ...

We address the problem of segmenting 3D scan data into objects or object classes. Our segmentation framework is based on a subclass of Markov Random Fields (MRFs) which support efficient graph-cut...

Word-Sense Disambiguation for Machine Translation (2005)

David Vickrey, Luke Biewald, Marc Teyssier, Daphne Koller

In word sense disambiguation, a system attempts to determine the sense of a word from contextual features. Major barriers to building a high-performing word sense disambiguation system include the...

AND THE COMMITTEE ON GRADUATE STUDIES (2004)

Markov networks are extensively used to model complex sequential, spatial, and relational interactions in fields as diverse as image processing, natural language analysis, and bioinformatics....

Ben Taskar, Daphne Koller, Andrew Y. Ng, Fernando Pereira

ii

Learning structured prediction models: a large margin approach (2004)

Markov networks are extensively used to model complex sequential, spatial, and relational interactions in fields as diverse as image processing, natural language analysis, and bioinformatics....

Ben Taskar, Vassil Chatalbashev, Daphne Koller, Carlos Guestrin

We consider large margin estimation in a broad range of prediction models where inference involves solving combinatorial optimization problems, for example, weighted graphcuts or matchings. Our goal...

Dragomir Anguelov, Praveen Srinivasan, Hoi-cheung Pang, Daphne Koller

We present an unsupervised algorithm for registering 3D surface scans of an object undergoing significant deformations. Our algorithm does not need markers, nor does it assume prior knowledge about...

Probabilistic models for relational data (2004)

David Heckerman, Christopher Meek, Daphne Koller

We introduce a graphical language for relational data called the probabilistic entityrelationship (PER) model. The model is an extension of the entity-relationship model, a common model for the...

Learning structured prediction models: a large margin approach (2004)

Ben Taskar, Vassil Chatalbashev, Daphne Koller, Carlos Guestrin

We consider large margin estimation in a broad range of prediction models where inference involves solving combinatorial optimization problems, for example, weighted graphcuts or matchings. Our goal...

FastSLAM: An efficient solution to the simultaneous localization and mapping problem with unknown data association (2004)

Markov networks are extensively used to model complex sequential, spatial, and relational interactions in fields as diverse as image processing, natural language analysis, and bioinformatics....

Sebastian Thrun, Michael Montemerlo, Daphne Koller, Ben Wegbreit, Juan Nieto, Eduardo Nebot

This article provides a comprehensive description of FastSLAM, a new family of algorithms for the simultaneous localization and mapping problem, which specifically address hard data association...

Learning structured prediction models: a large margin approach (2004)

Ben Taskar, Vassil Chatalbashev, Daphne Koller, Carlos Guestrin

We consider large margin estimation in a broad range of prediction models where inference involves solving combinatorial optimization problems, for example, weighted graphcuts or matchings. Our goal...

Recovering articulated object models from 3D range data (2004)

Dragomir Anguelov, Daphne Koller, Hoi-cheung Pang, Praveen Srinivasan, Sebastian Thrun

We address the problem of unsupervised learning of complex articulated object models from 3D range data. We describe an algorithm whose input is a set of meshes corresponding to different...

Recovering articulated object models from 3D range data (2004)

Dragomir Anguelov, Daphne Koller, Hoi-cheung Pang, Praveen Srinivasan, Sebastian Thrun

We address the problem of unsupervised learning of complex articulated object models from 3D range data. We describe an algorithm whose input is a set of meshes corresponding to different...

Dragomir Anguelov, Daphne Koller, Praveen Srinivasan, Hoi-cheung Pang

Markov networks are extensively used to model complex sequential, spatial, and relational interactions in fields as diverse as image processing, natural language analysis, and bioinformatics....

Figure 1: Several frames from a motion animation generated by interpolating two scans of a puppet (far left and far right), which were automatically registered using the Correlated Correspondence...

Learning structured prediction models: a large margin approach (2004)

Ben Taskar, Vassil Chatalbashev, Daphne Koller, Carlos Guestrin

We consider large margin estimation in a broad range of prediction models where inference involves solving combinatorial optimization problems, for example, weighted graphcuts or matchings. Our goal...

Link prediction in relational data (2004)

Ben Taskar, Ming-fai Wong, Pieter Abbeel, Daphne Koller

Many real-world domains are relational in nature, consisting of a set of objects related to each other in complex ways. This paper focuses on predicting the existence and the type of links between...

Representation Dependence in Probabilistic Inference (2003)

Halpern, Joseph Y., Koller, Daphne

Non-deductive reasoning systems are often {\em representation dependent}: representing the same situation in two different ways may cause such a system to return two different answers. Some have...

From Statistical Knowledge Bases to Degrees of Belief (2003)

Bacchus, Fahiem, Grove, Adam, Halpern, Joseph Y., Koller, Daphne

An intelligent agent will often be uncertain about various properties of its environment, and when acting in that environment it will frequently need to quantify its uncertainty. For example, if the...

Generalizing plans to new environments in relational MDPs (2003)

Carlos Guestrin, Daphne Koller, Chris Gearhart, Neal Kanodia

A longstanding goal in planning research is the ability to generalize plans developed for some set of environments to a new but similar environment, with minimal or no replanning. Such generalization...

A gene-coexpression network for global discovery of conserved genetic modules (2003)

Joshua M. Stuart, Eran Segal, Daphne Koller, Stuart K. Kim

To elucidate gene function on a global scale, we identified pairs of genes that are coexpressed over 3182 DNA microarrays from humans, flies, worms, and yeast. We found 22,163 such coexpression...

Link prediction in relational data (2003)

Ben Taskar, Ming-fai Wong, Pieter Abbeel, Daphne Koller

Many real-world domains are relational in nature, consisting of a set of objects related to each other in complex ways. This paper focuses on predicting the existence and the type of links between...

Generalizing plans to new environments in relational MDPs (2003)

Carlos Guestrin, Daphne Koller, Chris Gearhart, Neal Kanodia

A longstanding goal in planning research is the ability to generalize plans developed for some set of environments to a new but similar environment, with minimal or no replanning. Such generalization...

Max-margin Markov networks (2003)

A gene-coexpression network for global discovery of conserved genetic modules (2003)

In typical classification tasks, we seek a function which assigns a label to a single object. Kernel-based approaches, such as support vector machines (SVMs), which maximize the margin of confidence...

Joshua M. Stuart, Eran Segal, Daphne Koller, Stuart K. Kim

To elucidate gene function on a global scale, we identified pairs of genes that are coexpressed over 3182 DNA microarrays from humans, flies, worms, and yeast. We found 22,163 such coexpression...

Learning on the test data: Leveraging unseen features (2003)

Ben Taskar, Ming Fai Wong, Daphne Koller

This paper addresses the problem of classification in situations where the data distribution is not homogeneous: Data instances might come from different locations or times, and therefore are sampled...

Module Networks: Discovering Regulatory Modules and their Condition Specific Regulators from Gene Expression Data (2003)

Eran Segal, Michael Shapira, Aviv Regev, Dana Pe'er, David Botstein, Daphne Koller, ...

Introduction The complex functions of a living cell are carried out through the concerted activity of many genes and gene products. This activity is often coordinated by the organization of Computer...

FastSLAM 2.0: An Improved Particle Filtering Algorithm for Simultaneous Localization and Mapping that Provably Converges (2003)

Michael Montemerlo, Sebastian Thrun, Daphne Koller, Ben Wegbreit

In [15] , Montemerlo et al. proposed an algorithm called FastSLAM as an efficient and robust solution to the simultaneous localization and mapping problem. This paper describes a modified version of...

Efficient Solution Algorithms for Factored MDPs (2003)

Carlos Guestrin, Daphne Koller, Ronald Parr, Shobha Venkataraman

This paper addresses the problem of planning under uncertainty in large Markov Decision Processes (MDPs). Factored MDPs represent a complex state space using state variables and the transition model...

Max-Margin Markov Networks (2003)

Ben Taskar Carlos, Carlos Guestrin, Daphne Koller

In typical classification tasks, we seek a function which assigns a label to a single object. Kernel-based approaches, such as support vector machines (SVMs), which maximize the margin of confidence...

FastSLAM 2.0: An improved particle filtering algorithm for simultaneous localization and mapping that provably converges (2003)

Michael Montemerlo, Sebastian Thrun, Daphne Koller, Ben Wegbreit

In [15], Montemerlo et al. proposed an algorithm called FastSLAM as an efficient and robust solution to the simultaneous localization and mapping problem. This paper describes a modified version of...

AND THE COMMITTEE ON GRADUATE STUDIES (2003)

Carlos Ernesto Guestrin, Daphne Koller, Leslie Pack Kaelbling, Benjamin Van Roy

ii

AND THE COMMITTEE ON GRADUATE STUDIES (2003)

Carlos Ernesto Guestrin, Daphne Koller, Leslie Pack Kaelbling, Benjamin Van Roy

ii

Max-Margin Markov Networks (2003)

Ben Taskar Carlos, Carlos Guestrin, Daphne Koller

In typical classification tasks, we seek a function which assigns a label to a single object. Kernel-based approaches, such as support vector machines (SVMs), which maximize the margin of confidence...

Learning on the test data: Leveraging unseen features (2003)

Ben Taskar, Ming Fai Wong, Daphne Koller

This paper addresses the problem of classification in situations where the data distribution is not homogeneous: Data instances might come from different locations or times, and therefore are sampled...

Link prediction in relational data (2003)

Ben Taskar, Ming-fai Wong, Pieter Abbeel, Daphne Koller

Many real-world domains are relational in nature, consisting of a set of objects related to each other in complex ways. This paper focuses on predicting the existence and the type of links between...

Max-margin Markov networks (2003)

Max-margin Markov networks (2003)

3) networks incorporate both kernels, which efficiently deal with highdimensional features, and the ability to capture correlations in structured data.We present an efficient algorithm for learning M...

A continuation method for nash equilibria in structured games (2003)

In typical classification tasks, we seek a function which assigns a label to a single object. Kernel-based approaches, such as support vector machines (SVMs), which maximize the margin of confidence...

Ben Blum, Christian R. Shelton, Daphne Koller

Structured game representations have recently attracted interest as models for multiagent artificial intelligence scenarios, with rational behavior most commonly characterized by Nash equilibria....

2003, 'Label and Link Prediction in Relational Data (2003)

Ben Taskar, Pieter Abbeel, Ming-fai Wong, Daphne Koller

Many real-world domains are relational in nature, consisting of a set of entities linked to each other in complex ways. Two important tasks in such data are predicting entity labels and links between...

Max-Margin Markov Networks (2003)

Ben Taskar Carlos, Carlos Guestrin, Daphne Koller

In typical classification tasks, we seek a function which assigns a label to a single object. Kernel-based approaches, such as support vector machines (SVMs), which maximize the margin of confidence...

Link Prediction in Relational Data (2003)

Ben Taskar, Ming-fai Wong, Pieter Abbeel, Daphne Koller

Many real-world domains are relational in nature, consisting of a set of objects related to each other in complex ways. This paper focuses on predicting the existence and the type of links between...

Generalizing plans to new environments in relational MDPs (2003)

Carlos Guestrin, Daphne Koller, Chris Gearhart, Neal Kanodia

A longstanding goal in planning research is the ability to generalize plans developed for some set of environments to a new but similar environment, with minimal or no replanning. Such generalization...

Learning probabilistic models of link structure (2002)

Lise Getoor, Nit Friedman, Daphne Koller, Ben Taskar

Most real-world data is heterogeneous and richly interconnected. Examples include the Web, hypertext, bibliometric data and social networks. In contrast, most statistical learning methods work with...

Context specific multiagent coordination and planning with factored MDPs (2002)

Carlos Guestrin, Shobha Venkataraman, Daphne Koller

We present an algorithm for coordinated decision making in cooperative multiagent settings, where the agents ' value function can be represented as a sum of context-specific value rules. The...

Learning hierarchical object maps of non-stationary environments with mobile robots (2002)

Dragomir Anguelov, Rahul Biswas, Daphne Koller, Benson Limketkai, Scott Sanner, Sebastian Thrun

Building models, or maps, of robot environments is a highly active research area; however, most existing techniques construct unstructured maps and assume static environments. In this paper, we...

FastSLAM: A factored solution to the simultaneous localization and mapping problem (2002)

Michael Montemerlo, Sebastian Thrun, Daphne Koller, Ben Wegbreit

The ability to simultaneously localize a robot and accurately map its surroundings is considered by many to be a key prerequisite of truly autonomous robots. However, few approaches to this problem...

From promoter sequence to expression: A probabilistic framework (2002)

Eran Segal, Yoseph Barash, Itamar Simon, Nir Friedman, Daphne Koller

We present a probabilistic framework that models the process by which transcriptional binding explains the mRNA expression of different genes. Our joint probabilistic model unies the two key...

Hybrid Bayesian Networks for Reasoning About Complex Systems (2002)

N. Lerner, Daphne Koller, Stephen Boyd, Ronald Parr

ii

Context specific multiagent coordination and planning with factored MDPs (2002)

Carlos Guestrin, Shobha Venkataraman, Daphne Koller

We present a new, principled and efficient algorithm for decision making and planning cooperative multi-agent dynamic systems. We consider systems where the agents ' value function is a sum of...

FastSLAM: A Factored Solution to the Simultaneous Localization and Mapping Problem (2002)

Michael Montemerlo, Sebastian Thrun, Daphne Koller, Ben Wegbreit

The ability to simultaneously localize a robot and accurately map its surroundings is considered by many to be a key prerequisite of truly autonomous robots. However, few approaches to this problem...

Learning hierarchical object maps of non-stationary environments with mobile robots (2002)

Dragomir Anguelov, Rahul Biswas, Daphne Koller, Benson Limketkai, Scott Sanner, Sebastian Thrun

Building models, or maps, of robot environments is a highly active research area; however, most existing techniques construct unstructured maps and assume static environments. In this paper, we...

Simultaneous mapping and localization with sparse extended information filters (2002)

Sebastian Thrun, Daphne Koller, Zoubin Ghahramani, Hugh Durrant-whyte, Andrew Y. Ng

Abstract. This paper describes a scalable algorithm for the simultaneous mapping and localization (SLAM) problem. SLAM is the problem of determining the location of environmental features with a...

From Promoter Sequence to Expression: (2002)

Probabilistic Framework Eran, Eran Segal, Yoseph Barash, Itamar Simon, Nir Friedman, Daphne Koller

We present a probabilistic framework that models the process by which transcriptional binding explains the mRNA expression of different genes. Our joint probabilistic model unifies the two key...

Learning probabilistic models of link structure (2002)

Lise Getoor, Nir Friedman, Daphne Koller, Benjamin Taskar

Most real-world data is heterogeneous and richly interconnected. Examples include the Web, hypertext, bibliometric data and social networks. In contrast, most statistical learning methods work with...

Learning probabilistic models of link structure (2002)

Lise Getoor, Nir Friedman, Daphne Koller, Ben Taskar

Most real-world data is heterogeneous and richly interconnected. Examples include the Web, hypertext, bibliometric data and social networks. In contrast, most statistical learning methods work with...

Learning probabilistic models of link structure (2002)

Lise Getoor, Nir Friedman, Daphne Koller, Benjamin Taskar

Most real-world data is heterogeneous and richly interconnected. Examples include the Web, hypertext, bibliometric data and social networks. In contrast, most statistical learning methods work with...

Learning probabilistic models of link structure (2002)

Lise Getoor, Nir Friedman, Daphne Koller, Benjamin Taskar

Most real-world data is heterogeneous and richly interconnected. Examples include the Web, hypertext, bibliometric data and social networks. In contrast, most statistical learning methods work with...

Simultaneous mapping and localization with sparse extended information filters (2002)

Sebastian Thrun, Daphne Koller, Zoubin Ghahramani, Hugh Durrant-whyte, Andrew Y. Ng

Abstract. This paper describes a scalable algorithm for the simultaneous mapping and localization (SLAM) problem. SLAM is the problem of determining the location of environmental features with a...

Learning hierarchical object maps of non-stationary environments with mobile robots (2002)

Dragomir Anguelov, Rahul Biswas, Daphne Koller

Building models, or maps, of robot environments is a highly active research area; however, most existing techniques construct unstructured maps and assume static environments. In this paper, we...

Max-norm projections for factored MDPs (2001)

Structured models for multiagent interactions (2001)

Markov Decision Processes (MDPs) provide a coherent mathematical framework for planning under uncertainty. However, exact MDP solution algorithms require the manipulation of a value function, which...

Daphne Koller, Brian Milch

The traditional representations of games using the extensive form or the strategic (normal) form obscure much of the structure that is present in real-world games. In this paper, we propose a new...

Solving factored POMDPs with linear value functions (2001)

Multi-agent influence diagrams for representing and solving games (2001)

Partially Observable Markov Decision Processes (POMDPs) provide a coherent mathematical framework for planning under uncertainty when the state of the system cannot be fully observed. However, the...

Learning probabilistic models of relational structure (2001)

The traditional representations of games using the extensive form or the strategic (normal) form obscure much of the structure that is present in real-world games. In this paper, we propose a new...

Lise Getoor, Nit Friedman, Daphne Koller, Benjamin Taskar

Most real-world data is stored in relational form. In contrast, most statistical learning methods work with "flat " data representations, forcing us to convert our data into a form...

Learning probabilistic models of relational structure (2001)

Lise Getoor, Nir Friedman, Daphne Koller, Benjamin Taskar

Most real-world data is stored in relational form. In contrast, most statistical learning methods work with "flat " data representations, forcing us to convert our data into a form...

Probabilistic abstraction hierarchies (2001)

Multiagent planning with factored MDPs (2001)

Many domains are naturally organized in an abstraction hierarchy or taxonomy, where the instances in "nearby " classes in the taxonomy are similar. In this paper, we provide a...

Probabilistic abstraction hierarchies (2001)

We present a principled and efficient planning algorithm for cooperative multiagent dynamic systems. A striking feature of our method is that the coordination and communication between the agents is...

Multi-agent influence diagrams for representing and solving games (2001)

Many domains are naturally organized in an abstraction hierarchy or taxonomy, where the instances in "nearby " classes in the taxonomy are similar. In this paper, we provide a...

Daphne Koller, Brian Milch

The traditional representations of games using the extensive form or the strategic (normal) form obscure much of the structure that is present in real-world games. In this paper, we propose a new...

Probabilistic classification and clustering in relational data (2001)

Ben Taskar, Eran Segal, Daphne Koller

Supervised and unsupervised learning methods have traditionally focused on data consisting of independent instances of a single type. However, many real-world domains are best described by relational...

Max-norm projections for factored MDPs (2001)

Active Learning for Structure in Bayesian Networks (2001)

Markov Decision Processes (MDPs) provide a coherent mathematical framework for planning under uncertainty. However, exact MDP solution algorithms require the manipulation of a value function, which...

Max-norm projections for factored MDPs (2001)

The task of causal structure discovery from empirical data is a fundamental problem in many areas. Experimental data is crucial for accomplishing this task. However, experiments are typically...

Solving factored POMDPs with linear value functions (2001)

Markov Decision Processes (MDPs) provide a coherent mathematical framework for planning under uncertainty. However, exact MDP solution algorithms require the manipulation of a value function, which...

Exact inference in networks with discrete children of continuous parents (2001)

Partially Observable Markov Decision Processes (POMDPs) provide a coherent mathematical framework for planning under uncertainty when the state of the system cannot be fully observed. However, the...

Uri Lerner, Eran Segal, Daphne Koller

Many real life domains contain a mixture of discrete and continuous variables and can be modeled as hybrid Bayesian Networks (BNs). An important subclass of hybrid BNs are conditional linear Gaussian...

Probabilistic models of text and link structure for hypertext classification (2001)

Lise Getoor, Eran Segal, Ben Taskar, Daphne Koller

Most text classification methods treat each document as an independent instance. However, in many text domains, documents are linked and the topics of linked documents are correlated. For example,...

Sampling in factored dynamic systems (2001)

Daphne Koller, Uri Lerner

In many real-world domains, we are interested in monitoring the evolution of a complex situation over time. For example, we may be monitoring a patient's vital signs in an intensive care unit...

Active Learning for Structure in Bayesian Networks (2001)

Simon Tong Simon, Daphne Koller

The task of causal structure discovery from empirical data is a fundamental problem in many areas. Experimental data is crucial for accomplishing this task. However, experiments are typically...

Selectivity Estimation using Probabilistic Models (2001)

Lise Getoor Computer, Lise Getoor, Ben Taskar, Daphne Koller

Estimating the result size of complex queries that involve selection on multiple attributes and the join of several relations is a difficult but fundamental task in database query processing. It...

Multi-Agent Influence Diagrams for Representing and Solving Games (2001)

Daphne Koller Computer, Daphne Koller, Brian Milch

The traditional representations of games using the extensive form or the strategic (normal) form obscure much of the structure that is present in real-world games. In this paper, we propose a new...

Appeared in Advances in Neural Information Processing Systems NIPS-14, 2001. (2001)

Multiagent Planning With, Carlos Guestrin, Daphne Koller, Ronald Parr

We present a principled and efficient planning algorithm for cooperative multiagent dynamic systems. A striking feature of our method is that the coordination and communication between the agents is...

Probabilistic Hierarchical Clustering for Biological Data (2001)

Eran Segal, Daphne Koller

Biological data, such as gene expression profiles or protein sequences, is often organized in a hierarchy of classes, where the instances assigned to "nearby" classes in the tree are...

AND THE COMMITTEE ON GRADUATE STUDIES (2001)

Simon Tong, Daphne Koller, David Heckerman, Christopher Manning

ii

AND THE COMMITTEE ON GRADUATE STUDIES (2001)

Simon Tong, Daphne Koller, David Heckerman, Christopher Manning

ii

Multi-agent influence diagrams for representing and solving games (2001)

Daphne Koller, Brian Milch

The traditional representations of games using the extensive form or the strategic form obscure much of the structure of real-world games. In this paper, we propose a graphical representation for...

Multi-agent influence diagrams for representing and solving games (2001)

Rich probabilistic models for gene expression (2001)

The traditional representations of games using the extensive form or the strategic (normal) form obscure much of the structure that is present in real-world games. In this paper, we propose a new...

Segal, Eran, Taskar, Ben, Gasch, Audrey, Friedman, Nir, Koller, Daphne

Clustering is commonly used for analyzing gene expression data. Despite their successes, clustering methods suffer from a number of limitations. First, these methods reveal similarities that exist...

Semantics and Inference for Recursive Probability Models (2000)

Avi Pfeffer, Daphne Koller

In recent years, there have been several proposals that extend the expressive power of Bayesian networks with that of relational models. These languages open the possibility for the specification of...

Support vector machine active learning with applications to text classification (2000)

Abstract. Support vector machines have met with significant success in numerous real-world learning tasks. However, like most machine learning algorithms, they are generally applied using a randomly...

Support vector machine active learning with applications to text classification (2000)

Abstract. In many domains, we are interested in analyzing the structure of the underlying distribution, e.g., whether one variable is a direct parent of the other. Bayesian model selection attempts...

Simon Tong, Daphne Koller, Pack Kaelbling

Support vector machines have met with significant success in numerous real-world learning tasks. However, like most machine learning algorithms, they are generally applied using a randomly selected...

Active Learning for Parameter Estimation in Bayesian Networks (2000)

Support vector machine active learning with applications to text classification (2000)

Bayesian networks are graphical representations of probability distributions. In virtually all of the work on learning these networks, the assumption is that we are presented with a data set...

Discovering hidden variables: A structure-based approach (2000)

Abstract. Support vector machines have met with significant success in numerous real-world learning tasks. However, like most machine learning algorithms, they are generally applied using a randomly...

Gal Elidan, Noam Lotner, Nir Friedman, Daphne Koller

A serious problem in learning probabilistic models is the presence of hidden variables. These variables are not observed, yet interact with several of the observed variables. As such, they induce...

Discovering hidden variables: A structure-based approach (2000)

Gal Elidan, Noam Lotner, Nir Friedman, Daphne Koller

A serious problem in learning probabilistic models is the presence of hidden variables. These variables are not observed, yet interact with several of the observed variables. As such, they induce...

Support vector machine active learning with applications to text classification (2000)

Simon Tong, Daphne Koller, Pack Kaelbling

Support vector machines have met with signicant success in numerous real-world learning tasks. However, like most machine learning algorithms, they are generally applied using a randomly selected...

In many domains, we are interested in analyzing the structure of the underlying distribution, e.g., whether one variable is a direct parent of the other. Bayesian model-selection attempts to find the...

Policy iteration for factored MDPs (2000)

Abstract. In many multivariate domains, we are interested in analyzing the dependency structure of the underlying distribution, e.g., whether two variables are in direct interaction. We can represent...

Daphne Koller, Ronald Parr

Many large MDPs can be represented compactly using a dynamic Bayesian network. Although the structure of the value function does not retain the structure of the process, recent work has suggested...

Discovering hidden variables: A structure-based approach (2000)

Gal Elidan, Noam Lotner, Nir Friedman, Daphne Koller

A serious problem in learning probabilistic models is the presence of hidden variables. These variables are not observed, yet interact with several of the observed variables. As such, they induce...

Learning Probabilistic Relational Models with Structural Uncertainty (2000)

Lise Getoor, Daphne Koller, Benjamin Taskar, Nir Friedman

Most real-world data is stored in relational form. In contrast, most statistical learning methods, e.g., Bayesian network learning, work only with "flat " data representations,...

Discovering hidden variables: A structure-based approach (2000)

In many domains, we are interested in analyzing the structure of the underlying distribution, e.g., whether one variable is a direct parent of the other. Bayesian model-selection attempts to find the...

Gal Elidan, Noam Lotner, Nir Friedman, Daphne Koller

A serious problem in learning probabilistic models is the presence of hidden variables. These variables are not observed, yet interact with several of the observed variables. As such, they induce...

Probabilistic models for agents’ beliefs and decisions (2000)

Brian Milch, Daphne Koller

Many applications of intelligent systems require reasoning about the mental states of agents in the domain. We may want to reason about an agent's beliefs, including beliefs about other agents;...

Active Learning for Parameter Estimation in Bayesian Networks (2000)

Utilities as Random Variables: Density Estimation and Structure Discovery (2000)

Bayesian networks are graphical representations of probability distributions. In virtually all of the work on learning these networks, the assumption is that we are presented with a data set...

Urszula Chajewska, Daphne Koller

Decision theory does not traditionally include uncertainty over utility functions. We argue that the a person 's utility value for a given outcome can be treated as we treat other domain...

Making Rational Decisions using Adaptive Utility Elicitation (2000)

Urszula Chajewska, Daphne Koller, Ronald Parr

Rational decision making requires full knowledge of the utility function of the person affected by the decisions. However, in many cases, the task of acquiring such knowledge is not feasible due to...

Restricted Bayes Optimal Classifiers (2000)

From Instances to Classes in Probabilistic Relational Models (2000)

We introduce the notion of restricted Bayes optimal classifiers. These classifiers attempt to combine the flexibility of the generative approach to classification with the high accuracy associated...

Lise Getoor, Daphne Koller, Nir Friedman

Probabilistic graphical models, in particular Bayesian networks, are useful models for representing statistical patterns in propositional domains. Recent work develops effective techniques for...

Support Vector Machine Active Learning with Applications to Text Classification (2000)

Using Feature Hierarchies in Bayesian Network Learning (Extended Abstract) (2000)

Support vector machines have met with significant success in numerous real-world learning tasks. However, like most machine learning algorithms, they are generally applied using a randomly selected...

Marie DesJardins, Lise Getoor, Daphne Koller

In recent years, researchers in statistics and the UAI community have developed an impressive body of theory and algorithmic machinery for learning Bayesian networks from data. Learned Bayesian...

Policy Iteration for Factored MDPs (2000)

Daphne Koller, Ronald Parr

Many large MDPs can be represented compactly using a dynamic Bayesian network. Although the structure of the value function does not retain the structure of the process, recent work has suggested...

Bayesian Fault Detection and Diagnosis in Dynamic Systems (2000)

Uri Lerner, Ronald Parr, Daphne Koller, Gautam Biswas

This paper addresses the problem of tracking and diagnosing complex systems with mixtures of discrete and continuous variables. This problem is a difficult one, particularly when the system dynamics...

Semantics and Inference for Recursive Probability Models (2000)

Avi Pfeffer, Daphne Koller

In recent years, there have been several proposals that extend the expressive power of Bayesian networks with that of relational models. These languages open the possibility for the specification of...

In Proceedings of the Seventeenth National Conference on Artificial Intelligence (AAAI-00), (2000)

Pages Austin Texas, Uri Lerner, Ronald Parr, Daphne Koller, Gautam Biswas

This paper addresses the problem of tracking and diagnosing complex systems with mixtures of discrete and continuous variables. This problem is a difficult one, particularly when the system dynamics...

In Proceedings of the Seventeenth National Conference on Artificial Intelligence (AAAI-00), (2000)

Pages Austin Texas, Simon Tong, Daphne Koller

We introduce the notion of restricted Bayes optimal classifiers.

In Proceedings of the Seventeenth National Conference on Artificial Intelligence (AAAI-00), (2000)

Pages Austin Texas, Urszula Chajewska, Daphne Koller, Ronald Parr

function of the person affected by the decisions. However, in many cases, the task of acquiring such knowledge is not feasible due to the size of the outcome space and the complexity of the utility...

Abstract. In many multivariate domains, we are interested in analyzing the dependency structure of the underlying distribution, e.g., whether two variables are in direct interaction. We can represent...

Support vector machine active learning with applications to text classification (2000)

Abstract. In many domains, we are interested in analyzing the structure of the underlying distribution, e.g., whether one variable is a direct parent of the other. Bayesian model selection attempts...

Support vector machine active learning with applications to text classification (2000)

Support vector machines have met with significant success in numerous real-world learning tasks. However, like most machine learning algorithms, they are generally applied using a randomly selected...

Simon Tong, Daphne Koller, Pack Kaelbling

Support vector machines have met with significant success in numerous real-world learning tasks. However, like most machine learning algorithms, they are generally applied using a randomly selected...

Active Learning for Parameter Estimation in Bayesian Networks (2000)

SPOOK: A system for probabilistic object-oriented knowledge representation (1999)

Bayesian networks are graphical representations of probability distributions. In virtually all of the work on learning these networks, the assumption is that we are presented with a data set...

Avi Pfeffer, Daphne Koller, Brian Milch, Ken T. Takusagawa

In previous work, we pointed out the limitations of standard Bayesian networks as a modeling framework for large, complex domains. We proposed a new, richly structured modeling language,...

Learning probabilistic relational models (1999)

Nir Friedman, Lise Getoor, Daphne Koller, Avi Pfeffer

A large portion of real-world data is stored in commercial relational database systems. In contrast, most statistical learning methods work only with "flat " data representations....

Efficient Reinforcement Learning in Factored MDPs (1999)

Michael Kearns, Daphne Koller

We present a provably efficient and near-optimal algorithm for reinforcement learning in Markov decision processes (MDPs) whose transition model can be factored as a dynamic Bayesian network (DBN)....

SPOOK: A system for probabilistic object-oriented knowledge representation (1999)

Avi Pfeffer, Daphne Koller, Brian Milch, Ken T. Takusagawa

In previous work, we pointed out the limitations of standard Bayesian networks as a modeling framework for large, complex domains. We proposed a new, richly structured modeling language,...

SPOOK: A system for probabilistic object-oriented knowledge representation (1999)

Avi Pfeffer, Daphne Koller, Brian Milch, Ken T. Takusagawa

In previous work, we pointed out the limitations of standard Bayesian networks as a modeling framework for large, complex domains. We proposed a new, richly structured modeling language,...

SPOOK: A system for probabilistic object-oriented knowledge representation (1999)

Avi Pfeffer, Daphne Koller, Brian Milch, Ken T. Takusagawa

In previous work, we pointed out the limitations of standard Bayesian networks as a modeling framework for large, complex domains. We proposed a new, richly structured modeling language,...

Discovering the hidden structure of complex dynamic systems (1999)

Xavier Boyen, Nir Friedman, Daphne Koller

Dynamic Bayesian networks provide a compact and natural representation for complex dynamic systems. However, in many cases, there is no expert available from whom a model can be elicited. Learning...

Exploiting the architecture of dynamic systems (1999)

Exploiting the architecture of dynamic systems (1999)

Abstract--- Consider the problem of monitoring the state of a complex dynamic system, and predicting its future evolution. Exact algorithms for this task typically maintain a belief state, or...

A general algorithm for approximate inference and its application to hybrid bayes nets (1999)

Consider the problem of monitoring the state of a complex dynamic system, and predicting its future evolution. Exact algorithms for this task typically maintain a belief state, or distribution over...

Computing factored value functions for policies in structured MDPs (1999)

The clique tree algorithm is the standard method for doing inference in Bayesian networks. It works by manipulating clique potentials--- distributions over the variables in a clique. While this...

Daphne Koller, Ronald Parr

Many large Markov decision processes (MDPs) can be represented compactly using a structured representation such as a dynamic Bayesian network. Unfortunately, the compact representation does not help...

Discovering the Hidden Structure of Complex Dynamic Systems (1999)

Xavier Boyen Computer, Xavier Boyen, Nir Friedman, Daphne Koller

Dynamic Bayesian networks provide a compact and natural representation for complex dynamic systems. However, in many cases, there is no expert available from whom a model can be elicited. Learning...

Bayes optimal hyperplanes ! maximal margin hyperplanes (1999)

Structured Representation of Complex Stochastic Systems (1999)

Maximal margin classifiers are a core technology in modern machine learning. They have strong theoretical justifications and have shown empirical successes. We provide an alternative justification...

Nir Friedman, Daphne Koller, Avi Pfeffer

This paper considers the problem of representing complex systems that evolve stochastically over time. Dynamic Bayesian networks provide a compact representation for stochastic processes....

Reinforcement Learning Using Approximate Belief States (1999)

Andres Rodriguez, Ronald Parr, Daphne Koller

The problem of developing good policies for partially observable Markov decision problems (POMDPs) remains one of the most challenging areas of research in stochastic planning. One line of research...

Discovering the Hidden Structure of Complex Dynamic Systems (1999)

Xavier Boyen, Nir Friedman, Daphne Koller

Dynamic Bayesian networks provide a compact and natural representation for complex dynamic systems. However, in many cases, there is no expert available from whom a model can be elicited. Learning...

Learning the Structure of Utility Functions (1999)

Urszula Chajewska, Daphne Koller

Utility functions are defined over a space which is exponential in the number of variables on which the utility depends. More compact representations of the utility are possible if we make certain...

SPOOK: A system for probabilistic object-oriented knowledge representation (1999)

Avi Pfeffer, Daphne Koller, Brian Milch, Ken T. Takusagawa

In previous work, we pointed out the limitations of standard Bayesian networks as a modeling framework for large, complex domains. We proposed a new, richly structured modeling language,...

Bayes Optimal Hyperplanes -> Maximal Margin Hyperplanes (1999)

Policy Search via Density Estimation (1999)

Maximal margin classifiers are a core technology in modern machine learning. They have strong theoretical justifications and have shown empirical successes. We provide an alternative justification...

Learning Probabilistic Relational Models (1999)

We propose a new approach to the problem of searching a space of stochastic controllers for a Markov decision process (MDP) or a partially observable Markov decision process (POMDP). Following...

Nir Friedman, Lise Getoor, Daphne Koller, Avi Pfeffer

A large portion of real-world data is stored in commercial relational database systems. In contrast, most statistical learning methods work only with "flat" data representations. Thus, to...

A General Algorithm for Approximate Inference and Its Application to Hybrid Bayes Nets (1999)

In Proceedings of the Sixteenth National Conference on Artificial Intelligence (AAAI-99), (1999)

The clique tree algorithm is the standard method for doing inference in Bayesian networks. It works by manipulating clique potentials --- distributions over the variables in a clique. While this...

Pages Orlando Florida, Xavier Boyen, Daphne Koller

Consider the problem of monitoring the state of a complex dynamic system, and predicting its future evolution. Exact algorithms for this task typically maintain a belief state, or distribution over...

Efficient Reinforcement Learning in Factored MDPs (1999)

Michael Kearns, Daphne Koller

We present a provably efficient and near-optimal algorithm for reinforcement learning in Markov decision processes (MDPs) whose transition model can be factored as a dynamic Bayesian network (DBN).

Computing factored value functions for policies in structured MDPs (1999)

A general algorithm for approximate inference and its application to hybrid bayes nets (1999)

Many large Markov decision processes (MDPs) can be represented compactly using a structured representation such as a dynamic Bayesian network. Unfortunately, the compact representation does not help...

First-Order Conditional Logic Revisited (1998)

The clique tree algorithm is the standard method for doing inference in Bayesian networks. It works by manipulating clique potentials — distributions over the variables in a clique. While this...

Friedman, Nir, Halpern, Joseph Y., Koller, Daphne

Conditional logics play an important role in recent attempts to formulate theories of default reasoning. This paper investigates first-order conditional logic. We show that, as for first-order...

Probabilistic Frame-Based Systems (1998)

Approximate learning of dynamic models (1998)

Two of the most important threads of work in knowledge representation today are frame-based representation systems (FRS's) and Bayesian networks (BNs). FRS's provide an excellent...

Structured representation of complex stochastic systems (1998)

Inference is a key component in learning probabilistic models from partially observable data. When learning temporal models, each of the many inference phases requires a complete traversal over a...

Nir Friedman, Daphne Koller, Avi Pfeffer

This paper considers the problem of representing complex systems that evolve stochastically over time. Dynamic Bayesian networks provide a compact representation for stochastic processes....

Tractable Inference for Complex Stochastic Processes (1998)

Tractable Inference for Complex Stochastic Processes (1998)

The monitoring and control of any dynamic system depends crucially on the ability to reason about its current status and its future trajectory. In the case of a stochastic system, these tasks...

Using Learning for Approximation in Stochastic Processes (1998)

The monitoring and control of any dynamic system depends crucially on the ability to reason about its current status and its future trajectory. In the case of a stochastic system, these tasks...

Daphne Koller, Raya Fratkina

To monitor or control a stochastic dynamic system, we need to reason about its current state. Exact inference for this task requires that we maintain a complete joint probability distribution over...

Tractable Inference for Complex Stochastic Processes (1998)

Approximate Learning of Dynamic Models (1998)

The monitoring and control of any dynamic system depends crucially on the ability to reason about its current status and its future trajectory. In the case of a stochastic system, these tasks...

Approximate Learning of Dynamic Models (1998)

Inference is a key component in learning probabilistic models from partially observable data. When learning temporal models, each of the many inference phases requires a complete traversal over a...

Using learning for approximation in stochastic processes (1998)

Inference is a key component in learning probabilistic models from partially observable data. When learning temporal models, each of the many inference phases requires a traversal over an entire long...

A general algorithm for approximate inference and its applciation to hybrid bayes nets (1998)

To monitor or control a stochastic dynamic system, we need to reason about its current state. Exact inference for this task requires that we maintain a complete joint probability distribution over...

Using probabilistic information in data integration (1997)

The clique tree algorithm is the standard method for doing inference in Bayesian networks. It works by manipulating clique potentials — distributions over the variables in a clique. While this...

Daniela Florescu, Daphne Koller

The goal of a mediator system is to provide users a uniform interface to the multitude of informa-tion sources. To translate user queries, given in a mediated schema, to queries on the data sources,...

Representations and Solutions for Game-Theoretic Problems (1997)

Hierarchically classifying documents using very few words (1997)

A system with multiple interacting agents (whether artificial or human) is often best analyzed using game-theoretic tools. Unfortunately, while the formal foundations are well-established, standard...

Hierarchically Classifying Documents Using Very Few Words (1997)

The proliferation of topic hierarchies for text documents has resulted in a need for tools that automatically classify new documents within such hierarchies. Existing classification schemes which...

Nonuniform Dynamic Discretization in Hybrid Networks (1997)

The proliferation of topic hierarchies for text documents has resulted in a need for tools that automatically classify new documents within such hierarchies. Existing classification schemes which...

Alexander Kozlov, Daphne Koller

We consider probabilistic inference in general hybrid networks, which include continuous and discrete variables in an arbitrary topology. We reexamine the question of variable discretization in a...

Update rules for parameter estimation in Bayesian networks (1997)

Eric Bauer, Daphne Koller, Yoram Singer

This paper re-examines the problem of parameter estimation in Bayesian networks with missing values and hidden variables from the perspective of recent work in on-line learning [12]. We provide a...

Nonuniform Dynamic Discretization in Hybrid Networks (1997)

Alexander V. Kozlov, Daphne Koller

We consider probabilistic inference in general hybrid networks, which include continuous and discrete variables in an arbitrary topology. We reexamine the question of variable discretization in a...

Object-Oriented Bayesian Networks (1997)

Effective Bayesian Inference for Stochastic Programs (1997)

Bayesian networks provide a modeling language and associated inference algorithm for stochastic domains. They have been successfully applied in a variety of medium-scale applications. However, when...

Daphne Koller, David Mcallester, Avi Pfeffer

In this paper, we propose a stochastic version of a general purpose functional programming language as a method of modeling stochastic processes. The language contains random choices, conditional...

Learning Probabilities for Noisy First-Order Rules (1997)

Hierarchically Classifying Documents Using Very Few Words (1997)

First-order logic is the traditional basis for knowledge representation languages. However, its applicability to many real-world tasks is limited by its inability to represent uncertainty. Bayesian...

Using Probabilistic Information in Data Integration (1997)

The proliferation of topic hierarchies for text documents has resulted in a need for tools that automatically classify new documents within such hierarchies. One can use existing classifiers by...

Daniela Florescu, Daphne Koller, Alon Levy

The goal of a mediator system is to provide users a uniform interface to the multitude of information sources. To translate user queries, given in a mediated schema, to queries on the data sources,...

P-CLASSIC: A tractable probabilistic description logic (1997)

Daphne Koller, Alon Levy, Avi Pfeffer

Knowledge representation languages invariably reflect a trade-off between expressivity and tractability. Evidence suggests that the compromise chosen by description logics is a particularly...

Effective Bayesian Inference for Stochastic Programs (1997)

Daphne Koller Stanford, Daphne Koller, David Mcallester, Avi Pfeffer

In this paper, we propose a stochastic version of a general purpose functional programming language as a method of modeling stochastic processes. The language contains random choices, conditional...

Using Probabilistic Information in Data Integration (1997)

Daniela Florescu, Daphne Koller, Alon Levy

The goal of a mediator system is to provide users a uniform interface to the multitude of information sources. To translate user queries, given in a mediated schema, to queries on the data sources,...

Adaptive Probabilistic Networks with Hidden Variables (1997)

John Binder, Daphne Koller, Stuart Russell, Keiji Kanazawa, Padhraic Smyth

. Probabilistic networks (also known as Bayesian belief networks) allow a compact description of complex stochastic relationships among several random variables. They are rapidly becoming the tool of...

Adaptive Probabilistic Networks with Hidden Variables (1997)

John Binder, Daphne Koller, Stuart Russell, Keiji Kanazawa, Padhraic Smyth

. Probabilistic networks (also known as Bayesian belief networks) allow a compact description of complex stochastic relationships among several random variables. They are used widely for uncertain...

Update rules for parameter estimation in Bayesian networks (1997)

Eric Bauer, Daphne Koller, Yoram Singer

This paper re-examines the problem of parameter estimation in Bayesian networks with missing values and hidden variables from the perspective of recent work in on-line learning [12]. We provide a...

P-CLASSIC: A tractable probabilistic description logic (1997)

Daphne Koller, Alon Levy, Avi Pfeffer

Knowledge representation languages invariably reflect a trade-off between expressivity and tractability. Evidence suggests that the compromise chosen by description logics is a particularly...

Effective Bayesian inference for stochastic programs (1997)

Object-oriented Bayesian networks (1997)

In this paper, we propose a stochastic version of a general purpose functional programming language as a method of modeling stochastic processes. The language contains random choices, conditional...

Team-Maxmin Equilibria (1997)

Bayesian networks provide a modeling language and associated inference algorithm for stochastic domains. They have been successfully applied in a variety of medium-scale applications. However, when...

Bernhard Von Stengel, Daphne Koller

this paper, we show that the adversary can use the teams' inability to coordinate in the following way: If the team members use a team-maxmin strategy profile, then the adversary has a mixed...

Learning probabilities for noisy first-order rules (1997)

Constructing flexible dynamic belief networks from first-order probabilistic knowledge bases (1996)

First-order logic is the traditional basis for knowledge representation languages. However, its applicability to many real-world tasks is limited by its inability to represent uncertainty. Bayesian...

Glesner, Sabine, Koller, Daphne

Constructing flexible dynamic belief networks from first-order probabilistic knowledge bases. (1996)

Glesner, Sabine, Koller, Daphne

First-order conditional logic revisited (1996)

Finding mixed strategies with small supports in extensive form games (1996)

Conditional logics play an important role in recent attempts to formulate theories of default reasoning. This paper investigates first-order conditional logic. We show that, as for first-order...

First-order conditional logic revisited (1996)

The complexity of algorithms that compute strategies or operate on them typically depends on the representation length of the strategies involved. One measure for the size of a mixed strategy is the...

Asymptotic conditional probabilities: the non-unary case (1996)

Conditional logics play an important role in recent attempts to formulate theories of default reasoning. This paper investigates first-order conditional logic. We show that, as for first-order...

Efficient Computation of Equilibria for Extensive Two-Person Games (1996)

Motivated by problems that arise in computing degrees of belief, we consider the problem of computing asymptotic conditional probabilities for first-order sentences. Given first-order sentences...

Daphne Koller, Nimrod Megiddo, Bernhard Von Stengel

. The Nash equilibria of a two-person, non-zero-sum game are the solutions of a certain linear complementarity problem (LCP). In order to use this for solving a game in extensive form, it is first...

Toward Optimal Feature Selection (1996)

Context-Specific Independence in Bayesian Networks (1996)

In this paper, we examine a method for feature subset selection based on Information Theory. Initially, a framework for defining the theoretically optimal, but computationally intractable, method for...

Craig Boutilier, Nir Friedman, Moises Goldszmidt, Daphne Koller

Bayesiannetworks provide a languagefor qualitatively representing the conditional independence properties of a distribution. This allows a natural and compact representation of the distribution,...

From Statistical Knowledge Bases to Degrees of Belief (1996)

Fahiem Bacchus Computer, Fahiem Bacchus, Computer Science Dept, Adam J. Grove, Joseph Y. Halpern, Daphne Koller

An intelligent agent will often be uncertain about various properties of its environment, and when acting in that environment it will frequently need to quantify its uncertainty. For example, if the...

Irrelevance and Conditioning in First-Order Probabilistic Logic (1996)

Daphne Koller, Joseph Y. Halpern

First-order probabilistic logic is a powerful knowledge representation language. Unfortunately, deductive reasoning based on the standard semantics for this logic does not support certain desirable...

Toward Optimal Feature Selection (1996)

From Statistical Knowledge Bases to Degrees of Belief (1996)

In this paper, we examine a method for feature subset selection based on Information Theory. Initially, a framework for defining the theoretically optimal, but computationally intractable, method for...

Fahiem Bacchus, Computer Science Dept, Adam J. Grove, Joseph Y. Halpern, Daphne Koller

An intelligent agent will often be uncertain about various properties of its environment, and when acting in that environment it will frequently need to quantify its uncertainty. For example, if the...

Context-Specific Independence in Bayesian Networks (1996)

Craig Boutilier, Nir Friedman, Moises Goldszmidt, Daphne Koller

Bayesiannetworks provide a languagefor qualitatively representing the conditional independence properties of a distribution. This allows a natural and compact representation of the distribution,...

Toward Optimal Feature Selection (1996)

Context-Specific Independence in Bayesian Networks (1996)

In this paper, we examine a method for feature subset selection based on Information Theory. Initially, a framework for defining the theoretically optimal, but computationally intractable, method for...

Craig Boutilier, Nir Friedman, Moises Goldszmidt, Daphne Koller

Bayesiannetworks provide a languagefor qualitatively representing the conditional independence properties of a distribution. This allows a natural and compact representation of the distribution,...

Irrelevance and Conditioning in First-Order Probabilistic Logic (1996)

Daphne Koller, Joseph Y. Halpern

First-order probabilistic logic is a powerful knowledge representation language. Unfortunately, deductive reasoning based on the standard semantics for this logic does not support certain desirable...

Efficient Computation of Equilibria for Extensive Two-Person Games (1996)

Two-person Games, Daphne Koller, Nimrod Megiddo, Bernhard Von Stengel

. The Nash equilibria of a two-person, non-zero-sum game are the solutions of a certain linear complementarity problem (LCP). In order to use this for solving a game in extensive form, the game must...

From Statistical Knowledge Bases to Degrees of Belief (1996)

Fahiem Bacchus Computer, Fahiem Bacchus, Computer Science Dept, Adam J. Grove, Joseph Y. Halpern, Daphne Koller

An intelligent agent will often be uncertain about various properties of its environment, and when acting in that environment it will frequently need to quantify its uncertainty. For example, if the...

Irrelevance and conditioning in first-order probabilistic logic (1996)

Finding mixed strategies with small supports in extensive form games (1996)

First-order probabilistic logic is a powerful knowledge representation language. Unfortunately, deductive reasoning based on the standard semantics for this logic does not support certain desirable...

Irrelevance and conditioning in first-order probabilistic logic (1996)

Abstract: The complexity of algorithms that compute strategies or operate on them typically depends on the representation length of the strategies involved. One measure for the size of a mixed...

Efficient computation of equilibria for extensive two-person games (1996)

First-order probabilistic logic is a powerful knowledge representation language. Unfortunately, deductive reasoning based on the standard semantics for this logic does not support certain desirable...

Daphne Koller, Nimrod Megiddo, Bernhard Von Stengel

The Nash equilibria of a two-person, non-zero-sum game are the solutions of a certain linear complementarity problem (LCP). In order to use this for solving a game in extensive form, it is rst...

Representation dependence in probabilistic inference (1995)

Joseph Y. Halpern, Daphne Koller

Non-deductive reasoning systems are often representation dependent: representing the same situation in two di#erent ways may cause such a system to return two di#erent answers. Some have viewed this...

Generating and solving imperfect information games (1995)

Constructing Flexible Dynamic Belief Networks from First-Order Probabilistic Knowledge Bases (1995)

Work on game playing in AI has typically ignored games of imperfect information such as poker. In this paper, we present a framework for dealing with such games. We point out several important issues...

Sabine Glesner, Daphne Koller

Abstract. This paper investigates the power of first-order probabilistic logic (FOPL) as a representation language for complex dynamic situations. We introduce a sublanguage of FOPL and use it to...

Representation Dependence in Probabilistic Inference (1995)

Joseph Halpern, Daphne Koller

Non-deductive reasoning systems are often representation dependent: representing the same situation in two different ways may cause such a system to return two different answers. This is generally...

Constructing Flexible Dynamic Belief Networks from First-Order Probabilistic Knowledge Bases (1995)

Sabine Glesner, Daphne Koller

Abstract. This paper investigates the power of first-order probabilistic logic (FOPL) as a representation language for complex dynamic situations. We introduce a sublanguage of FOPL and use it to...

Representation Dependence in Probabilistic Inference (1995)

Joseph Halpern, Daphne Koller

Non-deductive reasoning systems are often representation dependent: representing the same situation in two different ways may cause such a system to return two different answers. This is generally...

Generating and Solving Imperfect Information Games (1995)

A Game-Theoretic Classification of Interactive Complexity Classes (1995)

Work on game playing in AI has typically ignored games of imperfect information such as poker. In this paper, we present a framework for dealing with such games. We point out several important issues...

Extend Ed, Joan Feigenbaum, Daphne Koller, Peter Shor

) Joan Feigenbaum AT&T Bell Labs, 2C-473 600 Mountain Avenue Murray Hill, NJ 07974-0636 jf@research.att.com Daphne Koller UC Berkeley Computer Science Division Berkeley, CA 94720...

A Game-Theoretic Classification of Interactive Complexity Classes (1995)

Extend Ed, Joan Feigenbaum, Daphne Koller, Peter Shor

) Joan Feigenbaum AT&T Bell Labs, 2C-473 600 Mountain Avenue Murray Hill, NJ 07974-0636 jf@research.att.com Daphne Koller UC Berkeley Computer Science Division Berkeley, CA 94720...

Finding Mixed Strategies with Small Supports in Extensive Form Games (1995)

A Game-Theoretic Classification of Interactive Complexity Classes (1995)

The complexity of algorithms that compute strategies or operate on them typically depends on the representation length of the strategies involved. One measure for the size of a mixed strategy is the...

Joan Feigenbaum, Daphne Koller, Peter Shor

Game-theoretic characterizations of complexity classes have often proved useful in understanding the power and limitations of these classes. One well-known example tells us that PSPACE can be...

Generating and solving imperfect information games (1995)

Generating and solving imperfect information games (1995)

Work on game playing in AI has typically ignored games of imperfect information such as poker. In this paper, we present a framework for dealing with such games. We point out several important issues...

Local learning in probabilistic networks with hidden variables (1995)

berkeley edu Work on game playing in AI has typically ignored games of imperfect information such as poker In this paper we present a framework for dealing with such games We point out several...

Stuart Russell, John Binder, Daphne Koller, Keiji Kanazawa

Probabilistic networks which provide compact descriptions of complex stochastic relationships among several random variables are rapidly becoming the tool of choice for uncertain reasoning in...

Constructing Flexible Dynamic Belief Networks from First-Order Probabilistic Knowledge Bases (1995)

Sabine Glesner, Daphne Koller

Abstract. This paper investigates the power of first-order probabilistic logic (FOPL) as a representation language for complex dynamic situations. We introduce a sublanguage of FOPL and use it to...

From knowledge to belief /--by Daphne Koller. (1994)

Koller, Daphne.

Cover title.

ARTICLE NO. 0051 Efficient Computation of Equilibria for Extensive (1994)

Two-person Games, Daphne Koller, Nimrod Megiddo, Bernhard Von Stengel

The Nash equilibria of a two-person, non-zero-sum game are the solutions of a certain linear complementarity problem (LCP). In order to use this for solving a game in extensive form, the game must...

Qualitative Planning under Assumptions: A Preliminary Report (1994)

Fast Algorithms for Finding Randomized Strategies in Game Trees (1994)

Most planners constructed up to now are qualitative: they deal with uncertainty by considering all possible outcomes of each plan, without quantifying their relative likelihood. They then choose a...

Daphne Koller, Nimrod Megiddo, Bernhard Von Stengel

Interactions among agents can be conveniently described by game trees. In order to analyze a game, it is important to derive optimal (or equilibrium) strategies for the different players. The...

(De)randomized Construction of Small Sample Spaces in NC (1994)

David R. Karger, Daphne Koller

Koller and Megiddo introduced the paradigm of constructing compact distributions that satisfy a given set of constraints, and showed how it can be used to efficiently derandomize certain types of...

A Response to "Believing on the basis of evidence" (1994)

Fahiem Bacchus, Adam Grove, Joseph Y. Halpern, Daphne Koller

This paper is essentially identical to one that appears in Computational Intelligence

Generating New Beliefs From Old (1994)

Fahiem Bacchus, Computer Science Dept, Adam J. Grove, Joseph Y. Halpern, Daphne Koller

In previous work [BGHK92, BGHK93], we have studied the random-worlds approach---a particular (and quite powerful) method for generating degrees of belief (i.e., subjective probabilities) from a...

Fast Algorithms for Finding Randomized Strategies in Game Trees (1994)

Daphne Koller, Nimrod Megiddo, Bernhard Von Stengel

Interactions among agents can be conveniently described by game trees. In order to analyze a game, it is important to derive optimal (or equilibrium) strategies for the different players. The...

Forming Beliefs About A Changing World (1994)

Fahiem Bacchus, Adam J. Grove, Joseph Y. Halpern, Daphne Koller

The situation calculus is a popular technique for reasoning about action and change. However, its restriction to a first-order syntax and pure deductive reasoning makes it unsuitable in many...

Generating New Beliefs From Old (1994)

Fahiem Bacchus, Computer Science Dept, Adam J. Grove, Joseph Y. Halpern, Daphne Koller

In previous work [BGHK92, BGHK93], we have studied the random-worlds approach---a particular (and quite powerful) method for generating degrees of belief (i.e., subjective probabilities) from a...

Forming Beliefs About a Changing World (1994)

Fahiem Bacchus, Adam J. Grove, Joseph Y. Halpern, Daphne Koller

The situation calculus is a popular technique for reasoning about action and change. However, its restriction to a firstorder syntax and pure deductive reasoning makes it unsuitable in many contexts....

Adaptive Probabilistic Networks (1994)

Stuart Russell, John Binder, Daphne Koller

Belief networks (or probabilistic networks) and neural networks are two forms of network representations that have been used in the development of intelligent systems in the field of artificial...

(De)randomized Construction of Small Sample Spaces in NC (1994)

David R. Karger, Daphne Koller

Koller and Megiddo introduced the paradigm of constructing compact distributions that satisfy a given set of constraints, and showed how it can be used to efficiently derandomize certain types of...

Random Worlds and Maximum Entropy (1994)

Fast Algorithms for Finding Randomized Strategies in Game Trees (1994)

Given a knowledge base KB containing first-order and statistical facts, we consider a principled method, called the random-worlds method, for computing a degree of belief that some formula '...

Daphne Koller, Nimrod Megiddo, Bernhard Von Stengel

Interactions among agents can be conveniently described by game trees. In order to analyze a game, it is important to derive optimal (or equilibrium) strategies for the different players. The...

From knowledge to belief / (1993)

Koller, Daphne.

Thesis (Ph. D.)--Stanford University, 1994.

Constructing small sample spaces satisfying given constraints (1993)

Daphne Koller, Nimrod Megiddo Y

Abstract. The subject of this paper is nding small sample spaces for joint distributions of n discrete random variables. Such distributions are often only required to obey a certain limited set of...

Finding the Hidden Path: Time Bounds for All-Pairs Shortest Paths (1993)

David R. Karger, Daphne Koller, Steven J. Phillips

. We investigate the all-pairs shortest paths problem in weighted graphs. We present an algorithm---the Hidden Paths Algorithm---that finds these paths in time O(m n+n 2 log n), where m is the number...

Finding the hidden path: Time bounds for all-pairs shortest paths (1993)

David R. Karger, Daphne Koller, Steven J. Phillips

We investigate the all-pairs shortest paths problem in weighted graphs. We present an algorithm---the Hidden Paths Algorithm---that finds these paths in time O(m

Asymptotic Conditional Probabilities: The Unary Case (1993)

Statistical Foundations for Default Reasoning (1993)

Motivated by problems that arise in computing degrees of belief, we consider the problem of computing asymptotic conditional probabilities for first-order sentences. Given first-order sentences...

Fahiem Bacchus, Computer Science Dept, Adam J. Grove, Jospeh Y. Halpern, Daphne Koller

We describe a new approach to default reasoning, based on a principle of indifference among possible worlds. We interpret default rules as extreme statistical statements, thus obtaining a knowledge...

Statistical Foundations for Default Reasoning (1993)

Fahiem Bacchus, Computer Science Dept, Adam J. Grove, Joseph Y. Halpern, Daphne Koller

We describe a new approach to default reasoning, based on a principle of indifference among possible worlds. We interpret default rules as extreme statistical statements, thus obtaining a knowledge...

Asymptotic Conditional Probabilities: The Non-unary Case (1993)

Constructing Small Sample Spaces Satisfying Given Constraints (1993)

Motivated by problems that arise in computing degrees of belief, we consider the problem of computing asymptotic conditional probabilities for first-order sentences. Given first-order sentences...

The complexity oftwo-person zero-sum games in extensive form (1992)

The subject of this paper is finding small sample spaces for joint distributions of n discrete random variables. Such distributions are often only required to obey a certain limited set of...

A Logic for Approximate Reasoning (1992)

This paper investigates the complexity of nding max-min strategies for nite two-person zero-sum games in the extensive form. The problem of determining whether a player with imperfect recall can...

Daphne Koller, Joseph Y. Halpern

We investigate the problem of reasoning with imprecise quantitative information. We give formal semantics to a notion of approximate observations, and define two types of entailment for a knowledge...

From Statistics to Beliefs (1992)

Fahiem Bacchus, Computer Science Dept, Adam Grove, Joseph Y. Halpern, Daphne Koller

An intelligent agent uses known facts, including statistical knowledge, to assign degrees of belief to assertions it is uncertain about. We investigate three principled techniques for doing this. All...

From Statistics to Beliefs (1992)

Fahiem Bacchus, Computer Science Dept, Adam Grove, Joseph Y. Halpern, Daphne Koller

An intelligent agent uses known facts, including statistical knowledge, to assign degrees of belief to assertions it is uncertain about. We investigate three principled techniques for doing this. All...

From Statistics to Beliefs (1992)

Fahiem Bacchus, Computer Science Dept, Adam Grove, Joseph Y. Halpern, Daphne Koller

An intelligent agent uses known facts, including statistical knowledge, to assign degrees of belief to assertions it is uncertain about. We investigate three principled techniques for doing this. All...

Asymptotic Conditional Probabilities for First-Order Logic (1992)

A Logic for Approximate Reasoning (1992)

Motivated by problems that arise in computing degrees of belief, we consider the problem of computing asymptotic conditional probabilities for first-order formulas. That is, given first-order...

Daphne Koller Stanford, Daphne Koller, Joseph Y. Halpern

We investigate the problem of reasoning with imprecise quantitative information. We give formal semantics to a notion of approximate observations, and define two types of entailment for a knowledge...

The Complexity of Two-Person Zero-Sum Games in Extensive Form (1990)

Sfp1 is a stress- and nutrient-sensitive regulator of ribosomal protein gene expression

This paper investigates the complexity of finding max-min strategies for finite two-person zero-sum games in the extensive form. The problem of determining whether a player with imperfect recall can...

Marion, Rosa M., Regev, Aviv, Segal, Eran, Barash, Yoseph, Koller, Daphne, Friedman, Nir, ...

Yeast cells modulate their protein synthesis capacity in response to physiological needs through the transcriptional control of ribosomal protein (RP) genes. Here we demonstrate that the...

Identifying regulatory mechanisms using individual variation reveals key role for chromatin modification

Lee, Su-In, Pe'er, Dana, Dudley, Aimée M., Church, George M., Koller, Daphne

Sequence polymorphisms affect gene expression by perturbing the complex network of regulatory interactions. We propose a probabilistic method, called Geronemo, which directly aims to identify the...

Multi-agent influence diagrams for representing and solving games

Koller, Daphne, Milch, Brian

Team-Maxmin Equilibria

Von Stengel, Bernhard, Koller, Daphne

Efficient Computation of Equilibria for Extensive Two-Person Games

Koller, Daphne, Megiddo, Nimrod, Von Stengel, Bernhard

The complexity of two-person zero-sum games in extensive form

Koller, Daphne, Megiddo, Nimrod

InSite: a computational method for identifying protein-protein interaction binding sites on a proteome-wide scale

Wang, Haidong, Segal, Eran, Ben-Hur, Asa, Li, Qian-Ru, Vidal, Marc, Koller, Daphne

InSite is a computational method that integrates high-throughput protein and sequence data to infer the specific binding regions of interacting protein pairs.

Finding Mixed Strategies with Small Supports in Extensive Form Games.

Koller, Daphne, Megiddo, Nimrod

Learning a Prior on Regulatory Potential from eQTL Data

Lee, Su-In, Dudley, Aimée M., Drubin, David, Silver, Pamela A., Krogan, Nevan J., Pe'er, Dana, ...

Genome-wide RNA expression data provide a detailed view of an organism's biological state; hence, a dataset measuring expression variation between genetically diverse individuals (eQTL data) may...

First-Order Conditional Logic Revisited

First-Order Conditional Logic Revisited

Conditional logics play an important role in recent attempts to investigate default reasoning. This paper investigates firstorder conditional logic. We show that, as for first-order probabilistic...

First-Order Conditional Logic Revisited

Conditional logics play an important role in recent attempts to formulate theories of default reasoning. This paper investigates first-order conditional logic. We show that, as for first-order...